Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18880
    Prev
    Next
    INDEX
    Explanations

    descriptions related to specific entities, such as "vampire Pam," "American wholesomeness," and "Hollywood hotel."

    oai_token-act-pair · gpt-3.5-turbo

    references to various cultural and societal stereotypes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.75
    icipated
    -0.68
    âķIJâķIJ
    -0.66
    TPPStreamerBot
    -0.57
     )]
    -0.57
    imately
    -0.56
     Ago
    -0.53
    staking
    -0.53
    é¾į
    -0.53
     sidx
    -0.51
    POSITIVE LOGITS
    eties
    0.63
    isms
    0.60
    smanship
    0.60
    gear
    0.58
    lon
    0.55
    vironments
    0.55
     outwe
    0.55
    tones
    0.55
    stros
    0.54
    unia
    0.53
    Activations Density 0.921%

    No Known Activations